Page 316 - IJB-9-6

International

Journal of Bioprinting

RESEARCH ARTICLE
Rheology-informed hierarchical machine

learning model for the prediction of printing
resolution in extrusion-based bioprinting

Dageon Oh , Masoud Shirzad , Min Chang Kim , Eun-Jae Chung , and
1
1
2
3
Seung Yun Nam *
1,2
1 Industry 4.0 Convergence Bionics Engineering, Pukyong National University, Busan 48513,
Republic of Korea
2 Major of Biomedical Engineering, Division of Smart Healthcare, Pukyong National University,
Busan 48513, Republic of Korea
3
Department of Otorhinolaryngology-Head and Neck Surgery, Seoul National University College of
Medicine, Seoul 03080, Republic of Korea

Abstract
In this study, a rheology-informed hierarchical machine learning (RIHML) model
was developed to improve the prediction accuracy of the printing resolution of
constructs fabricated by extrusion-based bioprinting. Specifically, the RIHML model,
as well as conventional models such as the concentration-dependent model and
printing parameter-dependent model, was trained and tested using a small dataset
of bioink properties and printing parameters. Interestingly, the results showed that
the RIHML model exhibited the lowest error percentage in predicting the printing
*Corresponding author: resolution for different printing parameters such as nozzle velocities and pressures,
Seung Yun Nam as well as for different concentrations of the bioink constituents. Besides, the RIHML
(synam@pknu.ac.kr)
model could predict the printing resolution with reasonably low errors even when
Citation: Oh D, Shirzad M, Kim MC, using a new material added to the alginate-based bioink, which is a challenging task
et al., 2023, Rheology-informed for conventional models. Overall, the results indicate that the RIHML model can be a
hierarchical machine learning
model for the prediction of printing useful tool to predict the printing resolution of extrusion-based bioprinting, and it is
resolution in extrusion-based versatile and expandable compared to conventional models since the RIHML model
bioprinting. Int J Bioprint, can easily generalize and embrace new data.
9(6): 1280.
https://doi.org/10.36922/ijb.1280
Received: March 16, 2023 Keywords: Bioprinting; Printability; Machine learning; Rheology; Printing resolution
Accepted: July 13, 2023
Published Online: August 9, 2023
Copyright: © 2023 Author(s).
This is an Open Access article 1. Introduction
distributed under the terms of the
Creative Commons Attribution In recent times, additive manufacturing approaches including three-dimensional (3D)
License, permitting distribution,
and reproduction in any medium, bioprinting have emerged as essential tools for fabricating artificial tissue and organ
provided the original work is constructs. Specifically, compared to conventional biofabrication methods, the 3D
properly cited. bioprinting technique can effectively deposit bioink layer by layer with a designed
Publisher’s Note: AccScience combination of biomaterials and living cells in desired locations and patterns [1-5] .
Publishing remains neutral with The primary bioprinting methods include inkjet-based bioprinting, extrusion-based
regard to jurisdictional claims in [6-9]
published maps and institutional bioprinting, and laser-assisted bioprinting . Among them, extrusion-based bioprinting
affiliations. has been the most widely used technique for research and commercial purposes. This is

Volume 9 Issue 6 (2023) 308 https://doi.org/10.36922/ijb.1280